Remote Real-Time Voice AI Engineer—Whisper & LLM

N-iX; Kraków; Hybrid; PLN 240,000 - 360,000; Full time

Benefits offered by this job

Flexible remote/office option

Salary and benefits package

Career growth and trainings

Education reimbursement

Team events

Job summary

N-iX is seeking a Voice AI Engineer (Real-time speech) to design and operate end-to-end voicebot pipelines on AWS, integrating Whisper ASR and Azerbaijani TTS, with low latency and high throughput targets. You will work across telephony and chat platforms, ensure data privacy, and drive MLOps pipelines.

The role emphasizes GPU optimization, container orchestration, and secure, compliant data handling within a hybrid cloud setup. Flexible remote options are available.

Qualifications

• 4+ years of hands-on experience with machine learning and Speech Processing with a primary focus on real-time conversational AI, ASR (STT), and TTS voice pipelines.
• Deep expertise with Amazon SageMaker (real-time GPU inference endpoints, Pipelines, Feature Store, Model Registry) and Amazon Bedrock (AgentCore, Bedrock Guardrails, Knowledge Bases).
• Proven track record in streaming speech inference, speech synthesis, and low-latency audio processing.
• Strong experience in GPU optimization and containerized orchestration (NVIDIA A100/L40S, AWS EC2 GPU instances, Docker, Kubernetes/EKS).
• Solid understanding of contact center and telephony platform integrations (Avaya, Genesys) and real-time decisioning interfaces.
• Proficient in Python, Redis (priority queuing & caching), and data security/privacy (FPE tokenization, handling sensitive/PII data).

Responsibilities

• Design, build, and operationalize end-to-end real-time STT → LLM → TTS voicebot pipelines on AWS, optimizing for streaming speech-to-text, first-token LLM generation, and first-audio TTS synthesis.
• Deploy and maintain production customer-trained Whisper (Azerbaijani ASR) and Azerbaijani TTS models as low-latency real-time endpoints on Amazon SageMaker and specialized GPU node pools (NVIDIA A100/L40S).
• Implement and manage the Bedrock Proxy Gateway on EKS for multi-model routing, priority queuing via Redis Sorted Sets, cost caps, and high-availability serving targeting ~200 rps without API throttling.
• Integrate voicebot and chatbot decision engines with core enterprise telephony and CVM platforms, including Avaya (voice telephony), Genesys (digital chat/omnichannel), and Pelatro (CVM offer decisioning and uplift models).
• Establish LLMOps & MLOps pipelines using Amazon SageMaker Pipelines and MLflow for experiment tracking, model versioning, prompt/agent registries, automated evaluation harnesses, and RAG knowledge base retrieval.
• Build call and chat transcription pipelines to ingest, transcribe, and extract real-time insights (churn risk, dissatisfaction, intent, lead signals) into downstream decision layers.
• Enforce data sovereignty and privacy controls by integrating on-premises Format Preserving Encryption (FPE) and tokenization wrappers into ML pipelines so zero raw PII enters AWS cloud environments.
• Define NFR baselines, dialogue flows, voicebot persona, turn-taking, and fallback/escalation logic to guarantee conversational round-trip latency.
• Automate ML deployment workflows using GitLab CI/CD and Infrastructure-as-Code (Terraform or AWS CDK), establishing observability and FinOps spend/anomaly monitoring via Amazon CloudWatch and Splunk.

Skills

Real-time

Speech processing

SageMaker

Bedrock

GPU optimization

Kubernetes/EKS

Python

Redis

Terraform/AWS CDK

GitLab CI/CD

Tools

AWS SageMaker

Amazon Bedrock

NVIDIA A100/L40S

Docker

Kubernetes

Job description

N-iX is seeking a Voice AI Engineer (Real-time speech) to design and operate end-to-end voicebot pipelines on AWS, integrating Whisper ASR and Azerbaijani TTS, with low latency and high throughput targets. You will work across telephony and chat platforms, ensure data privacy, and drive MLOps pipelines.

The role emphasizes GPU optimization, container orchestration, and secure, compliant data handling within a hybrid cloud setup. Flexible remote options are available.